ClawAudit verdict

openclaw-expert

openclaw-expert-guide

🟢 Trusted

Low risk — reviewed by ClawAudit, behavior matches stated purpose

Static reference index pointing to local documentation files covering OpenClaw architecture and configuration; no execution, no network calls, purely informational.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

security

transparency

maintenance

Findings (21)

Pattern match critical

Possible hardcoded credential

references/02-gateway.md · code · apiKey: "LITELLM_KEY

Pattern match critical

Pipe-to-shell pattern (curl | sh) — supply chain attack vector

references/09-installation.md · code · curl -fsSL https://openclaw.ai/install.sh | bash

Pattern match critical

Pipe to bash — executes piped content as shell commands

references/09-installation.md · code · | bash

Pattern match high

Accesses OpenClaw config/secrets directly

references/02-gateway.md · code · ~/.openclaw/.env

Pattern match high

References sudo — requests elevated privileges

references/02-gateway.md · code · sudo

Pattern match high

HTTP request to bare IP address — common in malicious payloads

references/02-gateway.md · code · http://127.0.0.1

Pattern match high

Instructs covert action — may act without user awareness

references/08-automation.md · code · silently

Pattern match high

Accesses shell history/config

references/09-installation.md · code · ~/.zshrc

Pattern match high

Recursive delete from root or home — destructive command

references/09-installation.md · prose · downgraded · rm -rf ~

Pattern match high

Pipe to sh — executes piped content as shell commands

references/09-installation.md · prose · downgraded · | sh

Pattern match high

Pipe to python — executes piped content as Python code

references/10-security-and-misc.md · prose · downgraded · | Python

Pattern match medium

References webhook/callback URL

references/04-channels.md · code · callbackUrl

Pattern match medium

Accesses cloud provider credentials

references/02-gateway.md · prose · downgraded · ~/.aws

Pattern match medium

References tunneling service

references/07-plugins.md · code · ngrok

Pattern match medium

apt-get install — installs system packages

references/09-installation.md · prose · downgraded · apt-get install

Pattern match medium

Sets world-executable permissions

references/11-platforms.md · code · chmod 700

Pattern match medium

Dynamic import() — loads module at runtime

references/12-reference.md · prose · downgraded · import (`

Pattern match low

Opens WebSocket connection

SKILL.md · prose · downgraded · WebSocket

Pattern match low

References agent memory files

references/06-tools.md · prose · downgraded · MEMORY.md

Pattern match low

Changes file ownership

references/09-installation.md · prose · downgraded · chown

Pattern match low

References agent configuration files

references/12-reference.md · prose · downgraded · agent-config

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/B/E/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API